Smart Tool for Earlier Prediction of Breast Cancer Using AI

Breast carcinoma is a commonly occurring medical condition, and early detection is essential for successful treatment. In terms of forecasting the danger of breast cancer, machine learning algorithms have produced encouraging results. In this study, we investigate how well the effective supervised algorithms CatBoost and XGBoost perform at detecting the existence of breast cancer. We took information from a publicly accessible dataset about the tumor size, texture, area, perimeter, and so on. We used a range of measures, including precision, recall, precision, accuracy, and F1-score, to gauge how well the models performed. Our results show that both XGBoost and CatBoost, having XGBoost scoring 93.5% and CatBoost scoring 92.3% respectively, are quite accurate in detecting the presence of breast cancer. Our work’s high degree of accuracy indicates these models can be a valuable tool for finding breast cancer early on. It also demonstrates the capability of employing efficient supervised algorithms for breast cancer prediction.